CN106303591B - A kind of video recommendation method and device - Google Patents
A kind of video recommendation method and device Download PDFInfo
- Publication number
- CN106303591B CN106303591B CN201510298553.4A CN201510298553A CN106303591B CN 106303591 B CN106303591 B CN 106303591B CN 201510298553 A CN201510298553 A CN 201510298553A CN 106303591 B CN106303591 B CN 106303591B
- Authority
- CN
- China
- Prior art keywords
- video
- information
- terminal user
- user group
- terminals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a kind of video recommendation methods, which comprises according to the metadata information for each terminal for playing video, each terminal is grouped, obtains several terminal user's groups；It for each terminal user's group, obtains the terminal user and organizes corresponding video recommendations table information, and organized to the terminal user and send a video recommendations table information.The embodiment of the invention also discloses a kind of video recommendations devices.
Description
Technical Field
The invention relates to the field of computer data processing, in particular to a video recommendation method and device.
Background
The appearance and popularization of the internet bring a great deal of information to users, and the pursuit of the users for the information in the information age is met. However, as the amount of information increases greatly, users cannot acquire useful information from a large amount of information, and the efficiency of information usage is reduced. The recommendation system solves the problem of information overload, and can recommend information which is possibly useful for the user according to the information requirement, interest, historical records and the like of the user, so that the user can find the required information more easily, and the use efficiency of the information is improved.
The existing recommendation system mainly obtains interest demand information and recommendation object characteristic information of a user, then uses a corresponding recommendation algorithm to perform matching calculation on the interest demand information and the recommendation object characteristic information of the user, finds a recommendation object which the user may be interested in, and then recommends the recommendation object to the user.
In the prior art, personalized recommendation is mostly performed for a single user, and a personalized recommendation object list is transmitted to each user, but the existing users using terminals are massive, and a lot of time and resources are needed for performing data analysis and then performing recommendation on each user terminal. In addition, for some bandwidth-limited networks, the existing recommendation method brings huge bandwidth consumption. If the application scene is to watch live programs by using the terminal, the number of the user terminals is very large, and if a personalized recommendation list corresponding to each user is generated for each user, huge bandwidth consumption is inevitably caused. For the behavior that the user terminal watches the live program, the most important bandwidth should be used for transmitting the live program signal, and the recommendation list is only one auxiliary information for watching the live program, and the recommendation list should not be transmitted by consuming too much bandwidth.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide a video recommendation method and apparatus, which can perform group recommendation on similar users, thereby saving time and resources and saving bandwidth.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a method of video recommendation, the method comprising:
grouping the terminals according to metadata information of the terminals playing the video to obtain a plurality of terminal user groups;
and aiming at each terminal user group, acquiring video recommendation table information corresponding to the terminal user group, and sending a copy of the video recommendation table information to the terminal user group.
In the above scheme, the grouping the terminals according to the metadata information of the terminals that have played the video to obtain a plurality of terminal user groups includes:
grouping the terminals according to metadata information of the terminals playing videos in a preset time period of a historical period to obtain a plurality of terminal user groups;
correspondingly, the sending of the video recommendation table information to the terminal user group includes:
and sending a piece of video recommendation table information to the terminal user group in the preset time period of the current day.
In the above scheme, the obtaining video recommendation table information corresponding to the terminal user group includes:
and taking the information of the video played by the terminal exceeding the first preset threshold in the terminal user group in the preset time period of the historical period as video recommendation table information to obtain the video recommendation table information.
In the above scheme, the obtaining video recommendation table information corresponding to the terminal user group includes:
grouping videos played by the terminal user group according to metadata information of videos played by the terminal user group in the historical period preset time period to obtain a video group corresponding to the terminal user group;
and taking the video information in the video group in which the video with the playing proportion exceeding a second preset threshold value in the corresponding video group as video recommendation table information to obtain the video recommendation table information.
In the above scheme, the video recommendation table information further carries information of terminals in the terminal user group, where the information of the terminals in the terminal user group is used to determine whether terminals in the terminal user group exist on a branch line when a transmission line is branched, and copy one piece of the video recommendation table information to the branch line when it is determined that terminals in the terminal user group exist on the branch line.
A video recommendation device, the device comprising:
the terminal grouping module is used for grouping the terminals by a user according to the metadata information of the terminals playing the video to obtain a plurality of terminal user groups;
the recommendation information acquisition module is used for acquiring video recommendation table information corresponding to the terminal user groups aiming at each terminal user group divided by the terminal grouping module;
and the recommendation information sending module is used for sending the corresponding video recommendation table information acquired by the recommendation information acquisition module to the terminal user group.
In the above scheme, the terminal grouping module is specifically configured to group the terminals according to metadata information of the terminals that have played videos within a preset time period in a historical period, so as to obtain a plurality of terminal user groups;
and the recommendation information sending module is used for sending the corresponding video recommendation table information acquired by the recommendation information acquisition module to the terminal user group in the preset time period of the current day.
In the above scheme, the recommendation information obtaining module is specifically configured to use information of videos played by terminals exceeding a first preset threshold in a terminal user group divided by the terminal grouping module within a preset time period of the historical period as a piece of video recommendation table information, so as to obtain the video recommendation table information.
In the above scheme, the apparatus further comprises a video grouping module;
the video grouping module is used for grouping videos played by the terminal user group according to metadata information of videos played by the terminal user group divided by the terminal grouping module in the preset time period of the historical period, and obtaining a video group corresponding to the terminal user group;
the recommendation information obtaining module is specifically configured to use, as video recommendation table information, video information in a video group in which a video with a play ratio exceeding a second preset threshold in a corresponding video group obtained by the video grouping module is located, and obtain the video recommendation table information.
In the above scheme, the video recommendation table information further carries information of terminals in the terminal user group, where the information of the terminals in the terminal user group is used to determine whether terminals in the terminal user group exist on a branch line when a transmission line is branched, and copy one piece of the video recommendation table information to the branch line when it is determined that terminals in the terminal user group exist on the branch line.
The embodiment of the invention provides a video recommendation method and device, which divide a large number of terminals into a plurality of terminal user groups according to some similar information and only send one piece of video recommendation table information for one terminal user group. Therefore, the corresponding video recommendation table information is obtained by performing data analysis on the terminal user group comprising a plurality of terminals only once, and time and resources are saved. In addition, only one piece of video recommendation table information is sent for one terminal user group, so that the consumption of bandwidth in the transmission process is greatly reduced, and the user can select the video to be watched by referring to the video recommendation table while the video transmission of a transmission line is not influenced.
Drawings
Fig. 1 is a schematic flowchart of a video recommendation method according to embodiment 1 of the present invention;
fig. 2 is a schematic flowchart of a video recommendation method according to embodiment 2 of the present invention;
fig. 3 is a block diagram of a video recommendation apparatus according to embodiment 3 of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
An embodiment of the present invention provides a video recommendation method, and as shown in fig. 1, a processing flow of the method of the present embodiment includes the following steps:
step 101, grouping the terminals according to the metadata information of the terminals playing the video to obtain a plurality of terminal user groups.
The recommendation device can group the terminals by using a parallelization clustering algorithm realized by MapReduce according to metadata information of each terminal playing the video within a period of time, such as the resolution of the terminal, and information of a browser and an application used by the terminal when the video is played, so that a plurality of terminal user groups can be obtained.
102, aiming at each terminal user group, obtaining video recommendation table information corresponding to the terminal user group, and sending a piece of video recommendation table information to the terminal user group.
After the recommending device groups the terminals, analyzing and obtaining a piece of video recommending table information corresponding to each terminal user group for each terminal user group, for example, assuming that in step 101, after the recommending device groups the terminals, the terminal 1-terminal 10 is a terminal user group, the recommending device analyzes the video played by the terminal 1-terminal 10 to obtain a piece of video recommending table information corresponding to the terminal user group; then, the recommending device sends a piece of video recommendation list information to the terminal 1-terminal 10 terminal user group.
Since the time when the user watches the video using the terminal is regularly circulated, the recommending device can recommend the video to the user at intervals, namely: grouping the terminals according to metadata information of the terminals playing videos in a preset time period of a historical period to obtain a plurality of terminal user groups; correspondingly, in the preset time period of the current day, sending a piece of video recommendation table information to the terminal user group.
Here, the recommending device may group the terminals according to metadata information of the terminals that have played videos within a preset time period of a historical period to obtain a plurality of terminal user groups; and then, taking the information of the video played by the terminal exceeding a first preset threshold value in the terminal user group in the preset time period of the historical period as video recommendation table information to obtain the video recommendation table information.
Assuming that the first preset threshold is 50%, in the historical period (one month before the day) in the evening 6: in the preset time period of 00-9:00, more than 50% of terminals in the user group of the terminal 1-terminal 10 play videos a, B and C, and then the recommendation device can send the information of the videos a, B and C to the terminal user group of the terminal 1-terminal 10 as a piece of video recommendation table information.
Or the recommending device can group the terminals according to metadata information of the terminals playing videos in a preset time period of a historical period to obtain a plurality of terminal user groups; then, according to metadata information of videos played by the terminal user group in the historical period preset time period, grouping the videos played by the terminal user group to obtain a video group corresponding to the terminal user group; and taking the video information in the video group in which the video with the playing proportion exceeding a second preset threshold value in the corresponding video group as video recommendation table information to obtain the video recommendation table information.
Since the terminals 1-10 in the user group may be at different positions, and the recommendation apparatus only sends one piece of video recommendation table information to one terminal user group, the recommendation apparatus broadcasts the video recommendation table information to a transmission line, when the transmission line has a bifurcation, if one of the terminals 1-10 is on the path after the bifurcation, one piece of the video recommendation table information is copied at the bifurcation, and if not, the copy is not needed. Therefore, the video recommendation table information also carries information of terminals in the terminal user group, and the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, so that a copy of the video recommendation table information is copied and transmitted to the branch line when the terminals in the terminal user group exist on the branch line.
In this embodiment, the terminal receives the video recommendation table information by using a pull model, and when there is video recommendation table information of a user group in which the terminal is located on the mobile communication base station, the terminal copies one piece of the video recommendation table information.
According to the method, a large number of terminals are divided into a plurality of terminal user groups according to some similar information, and only one piece of video recommendation table information is sent for one terminal user group. Therefore, the corresponding video recommendation table information is obtained by performing data analysis on the terminal user group comprising a plurality of terminals only once, and time and resources are saved. In addition, only one piece of video recommendation table information is sent for one terminal user group, so that the consumption of bandwidth in the transmission process is greatly reduced, and the user can select the video to be watched by referring to the video recommendation table while the video transmission of a transmission line is not influenced.
Example 2
An embodiment of the present invention provides a video recommendation method, and as shown in fig. 2, a processing flow of the method of the present embodiment includes the following steps:
step 201, grouping the terminals according to the metadata information of the terminals playing the video within the preset time period of the historical period to obtain a terminal user group.
The video described in this embodiment may be a live program, and in general, because the broadcast time of the live program is fixed, the time for the user to watch the live program using the terminal is regularly circulated, and the recommendation device may recommend the video to the user in different time periods, that is, the terminal that has played the live program in the past several days in the corresponding time period of the day recommends the corresponding live program.
The historical period is a period within a preset range from the current period, and the preset range should not be too large in value, because the videos watched by the user in the corresponding time period each day within a certain time range from the current day are more similar, and the types of the videos watched too long from the current day may be different from the current type, so in general, the historical period may be set to be a period within one month from the current period.
The preset time period is a certain time period in a day, for example, 24 hours a day can be divided into 8 time periods: 0:00-3:00, 3:00-6:00, 6:00-9:00, 9:00-12:00, 12:00-15:00, 15:00-18:00, 18:00-21:00, 21:00-24: 00. Assuming that the preset time period is 18:00-21:00, the recommending device may count the metadata information of each terminal that has played the video in the time period of 18:00-21:00 in the previous month, where the metadata information of the terminal is information such as the resolution of the terminal, the browser and the application used by the terminal when playing the video. The terminals may be grouped using a parallelized clustering algorithm implemented by MapReduce. Of course, the preset time period may also be other time periods in the day, and is not limited herein.
Step 202, grouping videos played by the end user group according to metadata information of videos played by the end user group in the preset time period of the historical period, and obtaining a video group corresponding to the end user group.
In step 201, dividing the terminal into a plurality of terminal user groups according to the metadata information of the terminal, wherein users in each user group have many similar preferences, and in this step, the recommendation device can play the metadata information of the video, such as the type and name of the video, according to the metadata information of the video played by the terminal user group in the preset time period of the historical period for each terminal user group; and calculating the similarity between the videos by using an Item-Based collaborative filtering algorithm realized Based on a MapReduce framework, wherein the aggregation with high similarity forms a video group. Thus, there are several video groups for each end user group.
Assuming that the terminal 1-terminal 10 that played video in the previous month in the time period of 18:00-21:00 is divided into a terminal user group in step 201, the terminal 1-terminal 10 user group may play video in the previous month in the time period of 18:00-21:00 in this step: video 1-video 100, grouped according to metadata information of these videos, and video 1-video 100 are divided into 10 video groups. I.e. terminal 1-terminal 10 correspond to 10 video groups.
And 203, taking the video information in the video group in which the video with the playing ratio exceeding a second preset threshold value in the corresponding video group as video recommendation table information, and obtaining the video recommendation table information.
Assuming that the playing numbers of the video a1 in the first video group, the video B2 in the second video group, and the video C3 in the third video group in the 10 video groups in step 202 exceed the second preset threshold, because the video in the video group in which the video a1 is located is a video having many similarities with the video a1, if the video a1 is preferred by the users in the end user group, it can be determined that the video in the video group in which the video a1 is located is also likely to be preferred by the users in the end user group, and therefore, the video information in the first video group in which the video a1 is located, the second video group in which the video B2 is located, and the third video group in which the video C3 is located are used as video recommendation table information.
Of course, in order to ensure that the videos recommended to the user are all favorite by the user, it may also be limited that the playing ratio exceeds the second preset threshold, and the ratio of the terminal playing the video to the terminal user group also exceeds the preset ratio, and the video information in the video group where the videos are located may be used as video recommendation table information to obtain the video recommendation table information.
And 204, sending a piece of video recommendation table information to the terminal user group in the preset time period of the current period.
And when the current day is in a preset time period of 18:00-21:00, the recommending device can send a piece of video recommendation table information to the terminal user group. Since the terminals 1-10 in the user group may be at different positions, and the recommendation apparatus only sends one piece of video recommendation table information to one terminal user group, the recommendation apparatus broadcasts the video recommendation table information to a transmission line, when the transmission line has a bifurcation, if one of the terminals 1-10 is on the path after the bifurcation, one piece of the video recommendation table information is copied at the bifurcation, and if not, the copy is not needed. Therefore, the video recommendation table information also carries information of terminals in the terminal user group, and the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, so that a copy of the video recommendation table information is copied and transmitted to the branch line when the terminals in the terminal user group exist on the branch line.
In this embodiment, the terminal receives the video recommendation table information by using a pull model, and when there is video recommendation table information of a group in which the terminal is located on the mobile communication base station, the terminal copies a copy of the video recommendation table information.
The recommendation device in this embodiment may have an offline state and an online state, and the recommendation device may perform step 201 and step 203 in the offline state to obtain video recommendation table information corresponding to each terminal user group in a preset time period, and perform step 204 in the online state to send a piece of corresponding video recommendation table information to each terminal user group in the preset time period of the current period. Of course, the recommending apparatus may also perform step 201 and step 203 in an online state, which is not limited herein.
The bottom framework of the recommendation device in the embodiment is a Hadoop platform, and is used for solving the problems of terminal grouping and video recommendation table generation under big data. In this embodiment, the metadata information of the terminal, the video played by the terminal in each time period, the time period in which the video is located, the metadata information of the video, and other information are stored in a Hadoop Distributed File System (HDFS).
Example 3
An embodiment of the present invention provides a video recommendation method, and as shown in fig. 3, an apparatus of this embodiment includes: a terminal grouping module 301, a recommendation information acquisition module 302, a recommendation information sending module 303, wherein,
a terminal grouping module 301, which is used for grouping the terminals by a user according to the metadata information of the terminals playing the video to obtain a plurality of terminal user groups;
a recommendation information obtaining module 302, configured to obtain, for each terminal user group divided by the terminal grouping module 301, video recommendation table information corresponding to the terminal user group;
a recommendation information sending module 303, configured to send a piece of the corresponding video recommendation table information obtained by the recommendation information obtaining module 302 to the terminal user group. The video recommendation table information also carries information of terminals in the terminal user group, and the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, so that the video recommendation table information is copied to the branch line when the terminals in the terminal user group exist on the branch line.
The terminal grouping module 301 is specifically configured to group terminals that have played videos within a preset time period of a historical period according to metadata information of the terminals, so as to obtain a plurality of terminal user groups; the recommendation information sending module 303 is configured to send the corresponding video recommendation table information obtained by the recommendation information obtaining module 302 to the terminal user group within the preset time period of the current day.
The recommendation information obtaining module 302 is specifically configured to use information of videos played by terminals exceeding a first preset threshold in the terminal user group divided by the terminal grouping module 301 in the preset time period of the historical period as video recommendation table information, so as to obtain the video recommendation table information.
As shown in fig. 3, the apparatus further comprises a video packetization module 304; wherein,
the video grouping module 304 is configured to group videos played by the end user group according to metadata information of videos played by the end user group divided by the end grouping module 301 within the preset time period of the historical period, and obtain a video group corresponding to the end user group;
the recommendation information obtaining module 302 is specifically configured to use, as video recommendation table information, video information in a video group in which a video with a play ratio exceeding a second preset threshold in a corresponding video group obtained by the video grouping module 304 is located, and obtain the video recommendation table information.
In practical applications, the terminal grouping module 301, the recommendation information obtaining module 302, the recommendation information sending module 303, and the video grouping module 304 in this embodiment may be implemented by devices such as a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), or a Field Programmable Gate Array (FPGA) on a server.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (9)
1. A method for video recommendation, the method comprising:
grouping the terminals according to metadata information of the terminals playing the video to obtain a plurality of terminal user groups;
the metadata information of the terminal comprises at least one of resolution of the terminal, a browser used when the video is played and an application;
aiming at each terminal user group, acquiring video recommendation table information corresponding to the terminal user group, and sending a copy of the video recommendation table information to the terminal user group;
the video recommendation table information also carries information of terminals in the terminal user group, the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, and the video recommendation table information is copied to the branch line when the terminals in the terminal user group exist on the branch line.
2. The method according to claim 1, wherein the grouping the terminals according to the metadata information of the terminals that have played the video to obtain a plurality of terminal user groups comprises:
grouping the terminals according to metadata information of the terminals playing videos in a preset time period of a historical period to obtain a plurality of terminal user groups;
correspondingly, the sending of the video recommendation table information to the terminal user group includes:
and sending a piece of video recommendation table information to the terminal user group in the preset time period of the current day.
3. The method according to claim 2, wherein the obtaining video recommendation table information corresponding to the terminal user group comprises:
and taking the information of the video played by the terminal exceeding the first preset threshold in the terminal user group in the preset time period of the historical period as video recommendation table information to obtain the video recommendation table information.
4. The method according to claim 2, wherein the obtaining video recommendation table information corresponding to the terminal user group comprises:
grouping videos played by the terminal user group according to metadata information of videos played by the terminal user group in the historical period preset time period to obtain a video group corresponding to the terminal user group;
and taking the video information in the video group in which the video with the playing proportion exceeding a second preset threshold value in the corresponding video group as video recommendation table information to obtain the video recommendation table information.
5. A video recommendation apparatus, characterized in that the apparatus comprises:
the terminal grouping module is used for grouping the terminals by a user according to the metadata information of the terminals playing the video to obtain a plurality of terminal user groups;
the metadata information of the terminal comprises at least one of resolution of the terminal, a browser used when the video is played and an application;
the recommendation information acquisition module is used for acquiring video recommendation table information corresponding to the terminal user groups aiming at each terminal user group divided by the terminal grouping module;
the recommendation information sending module is used for sending the corresponding video recommendation table information acquired by the recommendation information acquisition module to the terminal user group;
the video recommendation table information also carries information of terminals in the terminal user group, the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, and the video recommendation table information is copied to the branch line when the terminals in the terminal user group exist on the branch line.
6. The apparatus of claim 5,
the terminal grouping module is specifically used for grouping the terminals according to metadata information of the terminals playing videos in a preset time period of a historical period to obtain a plurality of terminal user groups;
and the recommendation information sending module is used for sending the corresponding video recommendation table information acquired by the recommendation information acquisition module to the terminal user group in the preset time period of the current day.
7. The apparatus of claim 6,
the recommendation information obtaining module is specifically configured to use information of videos played by terminals exceeding a first preset threshold in a terminal user group divided by the terminal grouping module within the preset time period of the historical period as video recommendation table information, and obtain the video recommendation table information.
8. The apparatus of claim 6, further comprising a video packet module;
the video grouping module is used for grouping videos played by the terminal user group according to metadata information of videos played by the terminal user group divided by the terminal grouping module in the preset time period of the historical period, and obtaining a video group corresponding to the terminal user group;
the recommendation information obtaining module is specifically configured to use, as video recommendation table information, video information in a video group in which a video with a play ratio exceeding a second preset threshold in a corresponding video group obtained by the video grouping module is located, and obtain the video recommendation table information.
9. The apparatus according to any one of claims 5 to 8,
the video recommendation table information also carries information of terminals in the terminal user group, the information of the terminals in the terminal user group is used for determining whether the terminals in the terminal user group exist on a branch line when a transmission line is branched, and the video recommendation table information is copied to the branch line when the terminals in the terminal user group exist on the branch line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510298553.4A CN106303591B (en) | 2015-06-03 | 2015-06-03 | A kind of video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510298553.4A CN106303591B (en) | 2015-06-03 | 2015-06-03 | A kind of video recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106303591A CN106303591A (en) | 2017-01-04 |
| CN106303591B true CN106303591B (en) | 2019-05-28 |
Family
ID=57655502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510298553.4A Active CN106303591B (en) | 2015-06-03 | 2015-06-03 | A kind of video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106303591B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107592572B (en) * | 2017-09-21 | 2021-05-14 | 广州方硅信息技术有限公司 | Video recommendation method, device and equipment |
| CN107493513B (en) * | 2017-09-29 | 2020-06-16 | 武汉斗鱼网络科技有限公司 | Method and device for measuring preference of user to live content |
| CN109063102B (en) * | 2018-07-27 | 2021-06-11 | 宁波光舟通信技术有限公司 | Data sending method and device of airborne intelligent equipment and airborne intelligent equipment |
| CN109068149B (en) * | 2018-09-14 | 2022-05-06 | 深圳Tcl新技术有限公司 | Program recommendation method, terminal and computer readable storage medium |
| CN113873287B (en) * | 2021-12-01 | 2022-03-15 | 泰德网聚(北京)科技股份有限公司 | Multi-line live broadcast method based on BS (base station) architecture |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103686237A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN103731738A (en) * | 2014-01-23 | 2014-04-16 | 哈尔滨理工大学 | Video recommendation method and device based on user group behavioral analysis |
| CN104333773A (en) * | 2013-12-18 | 2015-02-04 | 乐视网信息技术（北京）股份有限公司 | A Video recommending method and server |
-
2015
- 2015-06-03 CN CN201510298553.4A patent/CN106303591B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103686237A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN104333773A (en) * | 2013-12-18 | 2015-02-04 | 乐视网信息技术（北京）股份有限公司 | A Video recommending method and server |
| CN103731738A (en) * | 2014-01-23 | 2014-04-16 | 哈尔滨理工大学 | Video recommendation method and device based on user group behavioral analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106303591A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102054912B1 (en) | Channel Change Detection in Content-Aware Fingerprint Matching | |
| JP6818846B2 (en) | Automatic content recognition fingerprint sequence collation | |
| CN106303591B (en) | A kind of video recommendation method and device | |
| CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
| US11757749B2 (en) | Fusing online media monitoring data with secondary online data feeds to generate ratings data for online media exposure | |
| CN105163142B (en) | A kind of user preference determines method, video recommendation method and system | |
| CN104869439B (en) | A kind of video pushing method and device | |
| CN103024555B (en) | Based on television advertising detecting treatment system and the method for cloud computing | |
| WO2012173670A1 (en) | Systems and methods for providing media recommendations | |
| JP7053655B2 (en) | Target content placement using overlays | |
| CN103997662A (en) | Program pushing method and system | |
| US11252446B2 (en) | Employing automatic content recognition to allow resumption of watching interrupted media program from television broadcast | |
| KR102117922B1 (en) | Implementing interactive control of live television broadcast streams | |
| CN112015736B (en) | Multi-functional recommendation method and device based on Spark Mllib | |
| CN104301759A (en) | Television-watching time duration obtaining method and device | |
| CN114173200B (en) | Video management pushing method and device based on private radio and television network | |
| CN106817624B (en) | Method and device for analyzing behavior of user for reviewing program content |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |